From Text to Movement: LLM-driven Swarm User Interfaces for Embodied and Interactive Storytelling

This paper introduces PuppetLine, an interactive storytelling system that translates natural language narratives into coordinated performances using tabletop robots. The system combines large language models with a constrained set of action and emotion primitives to generate physically executable and interpretable multi-robot motions. We describe the system design and report findings from a designer-centered user study examining how people interpret and reflect on robot enactments. The results provide formative insights into mapping narrative intent to embodied interaction and inform the design of narrative Swarm User Interfaces.